langchain+chatgpt打造私有文档数据的问答系统代码

代码语言:python

所属分类:其他

代码描述:langchain+chatgpt打造私有文档数据的问答系统代码

代码标签: langchain chatgpt 打造 私有 文档 数据 问答 系统 代码

下面为部分代码预览,完整代码请点击下载或在bfwstudio webide中打开

#!/usr/local/python3/bin/python3
from llama_index import SimpleDirectoryReader, LangchainEmbedding, GPTListIndex,GPTSimpleVectorIndex, PromptHelper, LLMPredictor, ServiceContext
from langchain import OpenAI
import sys
import os
os.environ["OPENAI_API_KEY"] = 'openai的key'
def construct_index(directory_path):
    #max_input_size = 4096
    num_outputs = 2000  
    #max_chunk_overlap = 20
    #chunk_size_limit = 600
    #prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
    llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.7, model_name="gpt-3.5-turbo", max_tokens=num_outputs))
    documents = SimpleDirectoryReader(directory_path).load_data()
    #chunk_size_limit表示最大分块大小
    service_context = ServiceContext.from_defaults(llm_predictor=l.........完整代码请登录后点击上方下载按钮下载查看

网友评论0